Narrow Results

The original image transmission protocol based on WMSNs cannot meet the requirements for stable, reliable and real-time transmission because of the restricted transmission bandwidth and unstable communication link. To obtain abundant image information based on WMSNs, research on image transmission is necessary. In order to improve performance in terms of transmission reliability, transmission delay and node mortality, a multi-path crossed node rotation (MPCNR) protocol based on wireless sensor networks was proposed in this paper. The MPCNR protocol chooses multiple paths in parallel transmission expansion of bandwidth, puts forward the nodes with the same communication ability in each path, forming a cluster, and selects the most powerful node in the same cluster as a relay routing nodes to improves transmission stability and avoid large scale node death. A network simulation model by MATLAB was built to analyse the transmission reliability, the end-to-end delay and the number of surviving nodes. The simulation results show that, compared with the traditional image transmission protocol, the MPCNR protocol can improve performance in transmission reliability, transmission delay and node mortality. These findings are significant for image transmission based on wireless sensor networks.

LfD(Learning from Demonstration) has the advantage of requiring no expert knowledge about the robot itself, which make large-scale application of robots possible. In this paper, we present a novel approach based on combination of affine deformation and DMP(dynamic movement primitive) to deal with two fundamental problems in LfD: data gathering and policy deriving. In the proposed approach, demonstrated motion data are gathered from optical-based motion capture system and DMP is used to sketch feature and derive policy. Combined with affine deformation, joint trajectory derived from the control policy can be refined so that the manipulator's physical constraints satisfied, the end point accuracy preserved and the execution time optimized. We verify the feasibility of our approach by reproducing a series of different motions with various trajectory profiles on a humanoid robot's arm basing on limited human demonstrations.